SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fix the get_size_with_aspect_ratio in max_size situation (#30902)

Browse Source 
* fix the get_size_with_aspect_ratio in max_size situation

* make fix-up

* add more general solution

* consider when max_size is not defined

* fix typo

* fix typo

* simple fix

* fix error

* fix if else error

* fix error of size overwrite

* fix yolos image processing

* fix detr image processing

* make

* add longest related test script

* Update src/transformers/models/yolos/image_processing_yolos.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* add more test

* add test script about longest size

* remove deprecated

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
This commit is contained in:
Sangbum Daniel Choi
2024-06-04 00:12:08 +09:00
committed by GitHub
parent e4628434d8
commit 874ac129bb
10 changed files with 309 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
tests/models/grounding_dino/test_image_processing_grounding_dino.py
View File

@@ -575,3 +575,55 @@ class GroundingDinoImageProcessingTest(AnnotationFormatTestMixin, ImageProcessin
)
inputs = image_processor(images=[image_1, image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([2, 3, 150, 100]))
def test_longest_edge_shortest_edge_resizing_strategy(self):
image_1 = torch.ones([958, 653, 3], dtype=torch.uint8)
# max size is set; width < height;
# do_pad=False, longest_edge=640, shortest_edge=640, image=958x653 -> 640x436
image_processor = GroundingDinoImageProcessor(
size={"longest_edge": 640, "shortest_edge": 640},
do_pad=False,
)
inputs = image_processor(images=[image_1], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 640, 436]))
image_2 = torch.ones([653, 958, 3], dtype=torch.uint8)
# max size is set; height < width;
# do_pad=False, longest_edge=640, shortest_edge=640, image=653x958 -> 436x640
image_processor = GroundingDinoImageProcessor(
size={"longest_edge": 640, "shortest_edge": 640},
do_pad=False,
)
inputs = image_processor(images=[image_2], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 436, 640]))
image_3 = torch.ones([100, 120, 3], dtype=torch.uint8)
# max size is set; width == size; height > max_size;
# do_pad=False, longest_edge=118, shortest_edge=100, image=120x100 -> 118x98
image_processor = GroundingDinoImageProcessor(
size={"longest_edge": 118, "shortest_edge": 100},
do_pad=False,
)
inputs = image_processor(images=[image_3], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 98, 118]))
image_4 = torch.ones([128, 50, 3], dtype=torch.uint8)
# max size is set; height == size; width < max_size;
# do_pad=False, longest_edge=256, shortest_edge=50, image=50x128 -> 50x128
image_processor = GroundingDinoImageProcessor(
size={"longest_edge": 256, "shortest_edge": 50},
do_pad=False,
)
inputs = image_processor(images=[image_4], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 128, 50]))
image_5 = torch.ones([50, 50, 3], dtype=torch.uint8)
# max size is set; height == width; width < max_size;
# do_pad=False, longest_edge=117, shortest_edge=50, image=50x50 -> 50x50
image_processor = GroundingDinoImageProcessor(
size={"longest_edge": 117, "shortest_edge": 50},
do_pad=False,
)
inputs = image_processor(images=[image_5], return_tensors="pt")
self.assertEqual(inputs["pixel_values"].shape, torch.Size([1, 3, 50, 50]))